© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4832
    Prev
    Next
    INDEX
    Explanations

    language involving legal procedures and professions as well as age and time references.

    oai_token-act-pair · gemini-2.0-flash

    when

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.67
    kháu
    -0.61
    CPtr
    -0.61
     GenerationType
    -0.60
    OGND
    -0.60
     MediatR
    -0.58
    principalColumn
    -0.57
    mybatisplus
    -0.57
    GTCX
    -0.56
    After
    -0.56
    POSITIVE LOGITS
     when
    1.23
    when
    1.00
     quando
    0.94
     WHEN
    0.90
     cuando
    0.87
     When
    0.84
     Quando
    0.82
    When
    0.79
     lorsque
    0.79
    quando
    0.78
    Activations Density 1.038%

    No Known Activations